3 papers
cs.LG2022
ExpertNet: A Symbiosis of Classification and Clustering
Shivin Srivastava, Kenji Kawaguchi, Vaibhav Rajan
A widely used paradigm to improve the generalization performance of high-capacity neural models is through the addition of auxiliary unsupervised tasks during supervised training.…
cs.LG2021
MemStream: Memory-Based Streaming Anomaly Detection
Siddharth Bhatia, Arjit Jain, Shivin Srivastava +2
Given a stream of entries over time in a multi-dimensional data setting where concept drift is present, how can we detect anomalous activities? Most of the existing unsupervised an…
cs.LG2021
Clustering Aware Classification for Risk Prediction and Subtyping in Clinical Data
Shivin Srivastava, Siddharth Bhatia, Lingxiao Huang +3
In data containing heterogeneous subpopulations, classification performance benefits from incorporating the knowledge of cluster structure in the classifier. Previous methods for s…